Search

The current trend in the literature on Time Series Classification is to develop increasingly accurate algorithms by combining multiple models in ensemble hybrids, representing time series in complex and expressive feature spaces, and extracting features from different representations of the same time series. As a consequence of this focus on predictive performance, the best time series classifiers are black-box models, which are not understandable from a human standpoint. Even the approaches that are regarded as interpretable, such as shapelet-based ones, rely on randomization to maintain computational efficiency. This poses challenges for interpretability, as the explanation can change from run to run. Given these limitations, we propose the Bag-Of-Receptive-Field (BORF), a fast, interpretable, and deterministic time series transform. Building upon the classical Bag-Of-Patterns, we bridge the gap between convolutional operators and discretization, enhancing the Symbolic Aggregate Approximation (SAX) with dilation and stride, which can more effectively capture temporal patterns at multiple scales. We propose an algorithmic speedup that reduces the time complexity associated with SAX-based classifiers, allowing the extension of the Bag-Of-Patterns to the more flexible Bag-Of-Receptive-Fields, represented as a sparse multivariate tensor. The empirical results from testing our proposal on more than 150 univariate and multivariate classification datasets demonstrate good accuracy and great computational efficiency compared to traditional SAX-based methods and state-of-the-art time series classifiers, while providing easy-to-understand explanations.

With the rise of the Internet of Things (IoT), social networks, and mobile devices, vast amounts of mobility data are continuously generated. These data encompass diverse location information from various sources, including smart vehicles, sensors, wearables, and social media platforms. By leveraging these data, we explore the semantic enrichment of trajectory components related to moving objects and locations, bringing the so-called multiple-aspects trajectories and relative privacy issues. Privacy risk analysis is crucial for the earlier detection of privacy problems, particularly when dealing with semantically enriched trajectories. In this study, we introduced the TrajectGuard privacy risk assessment framework. TrajectGuard, an extension of PRUDEnce, achieved significant results by formulating and assessing the privacy risk of multiple-aspects trajectories under several proposed attacks. The framework introduced a nuanced risk evaluation using AspectGuard and conducted fair privacy assessments on anonymized datasets using AnonimoGuard. Its adaptability and versatility make TrajectGuard a valuable tool for preserving data privacy with multiple-aspects.

With the exponential growth of mobility data generated by IoT, social networks, and mobile devices, there is a pressing need to address privacy concerns. Our work proposes methods to reduce the computation of privacy risk evaluation on mobility datasets, focusing on reducing background knowledge configurations and matching functions, and enhancing code performance. Leveraging the unique characteristics of trajectory data, we aim to minimize the size of combination sets and directly evaluate risk for trajectories with distinct values. Additionally, we optimize efficiency by storing essential information in memory to eliminate unnecessary computations. These approaches offer a more efficient and effective means of identifying and addressing privacy risks associated with diverse mobility datasets.

Abstract Background Gastroesophageal reflux disease (GERD) is one of the most common gastrointestinal disorders worldwide, with relevant impact on the quality of life and health care costs.The aim of our study is to assess the prevalence of GERD based on self-reported symptoms among university students in central Italy. The secondary aim is to evaluate lifestyle correlates, particularly eating habits, in GERD students using automatically recorded transactions through cashiers at university canteen. Methods A web-survey was created and launched through an app, ad-hoc developed for an interactive exchange of information with students, including anthropometric data and lifestyle habits. Moreover, the web-survey allowed users a self-diagnosis of GERD through a simple questionnaire. As regard eating habits, detailed collection of meals consumed, including number and type of dishes, were automatically recorded through cashiers at the university canteen equipped with an automatic registration system. Results We collected 3012 questionnaires. A total of 792 students (26.2% of the respondents) reported typical GERD symptoms occurring at least weekly. Female sex was more prevalent than male sex. In the set of students with GERD, the percentage of smokers was higher, and our results showed that when BMI tends to higher values the percentage of students with GERD tends to increase. When evaluating correlates with diet, we found, among all users, a lower frequency of legumes choice in GERD students and, among frequent users, a lower frequency of choice of pasta and rice in GERD students. Discussion The results of our study are in line with the values reported in the literature. Nowadays, GERD is a common problem in our communities, and can potentially lead to serious medical complications; the economic burden involved in the diagnostic and therapeutic management of the disease has a relevant impact on healthcare costs. Conclusions To our knowledge, this is the first study evaluating the prevalence of typical GERD–related symptoms in a young population of University students in Italy. Considering the young age of enrolled subjects, our prevalence rate, relatively high compared to the usual estimates, could represent a further negative factor for the future economic sustainability of the healthcare system.

Abstract In this paper we investigate the regularities characterizing the temporal purchasing behavior of the customers of a retail market chain. Most of the literature studying purchasing behavior focuses on what customers buy while giving few importance to the temporal dimension. As a consequence, the state of the art does not allow capturing which are the temporal purchasing patterns of each customers. These patterns should describe the customer’s temporal habits highlighting when she typically makes a purchase in correlation with information about the amount of expenditure, number of purchased items and other similar aggregates. This knowledge could be exploited for different scopes: set temporal discounts for making the purchases of customers more regular with respect the time, set personalized discounts in the day and time window preferred by the customer, provide recommendations for shopping time schedule, etc. To this aim, we introduce a framework for extracting from personal retail data a temporal purchasing profile able to summarize whether and when a customer makes her distinctive purchases. The individual profile describes a set of regular and characterizing shopping behavioral patterns, and the sequences in which these patterns take place. We show how to compare different customers by providing a collective perspective to their individual profiles, and how to group the customers with respect to these comparable profiles. By analyzing real datasets containing millions of shopping sessions we found that there is a limited number of patterns summarizing the temporal purchasing behavior of all the customers, and that they are sequentially followed in a finite number of ways. Moreover, we recognized regular customers characterized by a small number of temporal purchasing behaviors, and changing customers characterized by various types of temporal purchasing behaviors. Finally, we discuss on how the profiles can be exploited both by customers to enable personalized services, and by the retail market chain for providing tailored discounts based on temporal purchasing regularity.

The biomedical field is characterized by an ever-increasing production of sequential data, which often come in the form of biosignals capturing the time-evolution of physiological processes, such as blood pressure and brain activity. This has motivated a large body of research dealing with the development of machine learning techniques for the predictive analysis of such biosignals. Unfortunately, in high-stakes decision making, such as clinical diagnosis, the opacity of machine learning models becomes a crucial aspect to be addressed in order to increase the trust and adoption of AI technology. In this paper, we propose a model agnostic explanation method, based on occlusion, that enables the learning of the input’s influence on the model predictions. We specifically target problems involving the predictive analysis of time-series data and the models that are typically used to deal with data of such nature, i.e., recurrent neural networks. Our approach is able to provide two different kinds of explanations: one suitable for technical experts, who need to verify the quality and correctness of machine learning models, and one suited to physicians, who need to understand the rationale underlying the prediction to make aware decisions. A wide experimentation on different physiological data demonstrates the effectiveness of our approach both in classification and regression tasks.

Students organize and manage their own learning time, choosing when, what, and how to study due to the flexibility of online learning. Each person has unique learning habits that define their behaviours and distinguish them from others. To investigate the temporal behaviour of students in online learning environments, we seek to identify suitable time-windows that could be used to investigate their temporal behaviour. First, we present a novel perspective for identifying different types of sessions based on individual needs. The majority of previous works address this issue by establishing an arbitrary session timeout threshold. In this paper, we propose an algorithm for determining the optimal threshold for a given session. Second, we use data-driven methods to support investigators in determining time-windows based on the identified sessions. To this end, we developed a visual tool that assists data scientists and researchers to determine the optimal settings for session identification and locating suitable time-windows.

The aim of this article is to synthetically describe the research projects that a selection of Italian universities is undertaking in the context of big data. Far from being exhaustive, this article has the objective of offering a sample of distinct applications that address the issue of managing huge amounts of data in Italy, collected in relation to diverse domains.